The sherpa.optmethods.optscipy module

Interface to Scipy optimization methods.

This module contains classes that wrap the optimization functions in scipy.optimize to match the calling signature and return values to the Sherpa interface.

If scipy is installed, classes are created automatically and can be used in the same way as other optimizers in Sherpa. The most versatile function is scipy.optimize.minimize, wrapped into the Scipy_Minimize class. scipy.optimize.minimize is itself a wrapper around several different optimization algorithms. Which one is used by default depends on the bounds places on the parameter values of the model to be fit.

scipy.optimize also contains several global optimizers that aim to explore the parameter space more fully. Most of these will only work if meaningful limits are placed in the parameters, see the scipy docs for global optimizers for details.

Classes

Scipy_Minimize([name])	Optimizer using scipy.optimize.minimize.
Scipy_Basinhopping([name])	Optimizer using scipy.optimize.basinhopping.
Scipy_DifferentialEvolution([name])	Optimizer using scipy.optimize.differential_evolution.
Scipy_DualAnnealing([name])	Optimizer using scipy.optimize.dual_annealing.
Scipy_Shgo([name])	Optimizer using scipy.optimize.shgo.
Scipy_Direct([name])	Optimizer using scipy.optimize.direct.

Class Inheritance Diagram